Research

The “PMBB Imaging and Clinical Data” course provides a comprehensive exploration of the integration and analysis of imaging and clinical data within the context of the Penn Medicine BioBank (PMBB). Students will learn how to handle diverse data types, including medical imaging, electronic health records (EHR), and genetic data, to drive biomedical research and precision medicine initiatives. The course emphasizes data preprocessing, feature extraction, and advanced analytical techniques to generate meaningful clinical insights. Hands-on experience with data tools and case studies from PMBB projects will equip students with the skills needed to harness complex datasets for impactful health outcomes and innovative research.

The “AI Pipelines in the Clinic” course focuses on developing and deploying end-to-end AI systems that enhance clinical workflows and patient care. Students will learn to design AI pipelines for data acquisition, preprocessing, model training, validation, and deployment within clinical settings, with a focus on safety, accuracy, and compliance with healthcare standards. The course emphasizes real-world challenges, such as data privacy, interpretability, and integration with existing clinical infrastructure. Through practical projects and case studies, participants will gain experience in building AI tools that support decision-making, improve diagnostics, and optimize patient outcomes in medical environments.

The “Senior Data Manager” course equips students with advanced skills and strategies for managing large and complex data ecosystems within organizations. Participants will learn to design, implement, and oversee data governance frameworks, ensuring data quality, compliance, and security. The course covers best practices for data integration, storage optimization, and lifecycle management, along with emerging trends in data technologies. Through case studies, real-world scenarios, and hands-on labs, students will develop leadership skills necessary to guide data-driven decision-making and drive organizational growth while effectively collaborating across technical and business teams.

This course delves into the ethical challenges and societal implications of AI technologies, focusing on reducing bias and promoting fairness in AI systems. Students will explore the sources and impacts of algorithmic bias, examine case studies of AI-driven discrimination, and learn methodologies to detect, measure, and mitigate bias in AI models. By engaging with ethical frameworks, regulatory guidelines, and technical strategies, participants will gain the tools necessary to develop more inclusive and equitable AI solutions. The course combines theory and practice to empower students to build AI systems that serve all segments of society fairly.

The “Causal AI Modeling” course introduces students to the critical principles and techniques of identifying and modeling cause-and-effect relationships using AI. Unlike traditional correlation-based approaches, this course emphasizes causal inference, enabling more robust and interpretable decision-making in diverse applications such as healthcare, economics, and social sciences. Students will learn how to construct, validate, and apply causal models using real-world data while exploring cutting-edge algorithms and tools that drive AI systems capable of reasoning about interventions and outcomes. Hands-on projects will deepen their understanding of how to build more transparent and actionable AI solutions.

Our “AI in Computational Pathology” mini-course offers students an in-depth look at the transformative role of artificial intelligence in medical diagnostics and research. Participants will explore how AI-driven image analysis, pattern recognition, and predictive models can enhance the accuracy and efficiency of disease detection and classification. The course emphasizes practical applications and cutting-edge research, preparing students to develop innovative solutions that advance healthcare and improve patient outcomes. Through hands-on projects and expert-led discussions, students will gain valuable skills in deploying AI tools tailored to the complexities of pathology.